Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5281
    Prev
    Next
    INDEX
    Explanations

    references to notable historical figures and their contributions in art

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meer
    -0.07
    lund
    -0.07
    arrera
    -0.07
    imore
    -0.06
     lava
    -0.06
    ymoon
    -0.06
    adium
    -0.06
    631
    -0.06
    chos
    -0.06
    èķ
    -0.06
    POSITIVE LOGITS
     Vinci
    0.12
     Leonardo
    0.12
     Flo
    0.09
     Renaissance
    0.08
     Mona
    0.08
     Leicester
    0.08
     Cod
    0.07
    Flo
    0.07
    Leon
    0.07
    raud
    0.07
    Activations Density 0.004%

    No Known Activations